© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 119923
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the most effective methods or strategies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PerformLayout
    -0.59
    Organisateur
    -0.55
     Inscrivez
    -0.51
    KURZBESCHREIBUNG
    -0.50
     diferente
    -0.50
    igshid
    -0.50
    URLException
    -0.49
    DllImport
    -0.49
    adaptiveStyles
    -0.48
    Soorten
    -0.48
    POSITIVE LOGITS
     best
    0.71
    best
    0.65
     BEST
    0.60
    Best
    0.56
     najlepiej
    0.55
    最好的
    0.54
     Best
    0.51
     beste
    0.47
     beſt
    0.47
     terbaik
    0.47
    Activations Density 0.026%

    No Known Activations